深度半监督迁移学习用于PET/CT上全自动全身肿瘤量化与癌症预后
这项回顾性研究纳入611例肺癌、黑色素瘤、淋巴瘤、头颈癌和乳腺癌患者的18F-FDG PET/CT及408例前列腺癌患者的PSMA PET/CT,开发了基于nnU-net主干的深度半监督迁移学习方法,实现全自动全身肿瘤分割与预后分析。方法在分割任务上获得中位真阳性率0.75–0.87、中位Dice相似系数0.73–0.83,并构建了前列腺癌风险分层、头颈癌生存估计和乳腺癌病理完全缓解预测模型。结论认为该方法在6种癌症类型的18F-FDG和PSMA PET/CT上展示了准确的肿瘤分割和预后评估。
要点
- 深度半监督迁移学习在6种癌症的18F-FDG和PSMA PET/CT上实现全自动肿瘤分割。
- 前列腺癌风险模型总体准确率0.83、AUC 0.86,低-中危与高危组随访PSA均值分别为18.61与727.46 ng/mL(P < 0.05)。
- 乳腺癌病理完全缓解预测仅用治疗前影像准确率0.72、AUC 0.72,联合治疗前后准确率0.84、AUC 0.76。
核心结论
- 所提出的方法在6种癌症类型的18F-FDG和PSMA PET/CT扫描上展示了准确的肿瘤分割和预后评估。
研究设计与样本
- 回顾性研究,纳入611例肺癌、黑色素瘤、淋巴瘤、头颈癌和乳腺癌患者的18F-FDG PET/CT扫描及408例前列腺癌患者的PSMA PET/CT扫描。
- 方法采用nnU-net主干,在有限标注和影像组学分析下学习18F-FDG和PSMA PET/CT图像的分割任务。
- 采用真阳性率和Dice相似系数评估分割性能,并利用预测分割提取的影像学指标构建预后模型。
主要发现
- 肺癌、黑色素瘤、淋巴瘤和前列腺癌患者肿瘤分割任务的中位真阳性率分别为0.75、0.85、0.87和0.75,中位Dice相似系数分别为0.81、0.76、0.83和0.73。
- 前列腺癌风险模型总体准确率为0.83,AUC为0.86;低-中危与高危患者平均随访前列腺特异性抗原水平分别为18.61与727.46 ng/mL(P < 0.05)。
- 头颈癌风险评分在单变量和多变量Cox回归分析中均与总生存显著相关(P < 0.05)。
- 乳腺癌病理完全缓解预测模型仅用治疗前影像指标时准确率为0.72、AUC为0.72,联合治疗前和治疗后指标时准确率为0.84、AUC为0.76。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
Automatic detection and characterization of cancer are important clinical needs to optimize early treatment. We developed a deep, semisupervised transfer learning approach for fully automated, whole-body tumor segmentation and prognosis on PET/CT. Methods: This retrospective study consisted of 611 18F-FDG PET/CT scans of patients with lung cancer, melanoma, lymphoma, head and neck cancer, and breast cancer and 408 prostate-specific membrane antigen (PSMA) PET/CT scans of patients with prostate cancer. The approach had a nnU-net backbone and learned the segmentation task on 18F-FDG and PSMA PET/CT images using limited annotations and radiomics analysis. True-positive rate and Dice similarity coefficient were assessed to evaluate segmentation performance. Prognostic models were developed using imaging measures extracted from predicted segmentations to perform risk stratification of prostate cancer based on follow-up prostate-specific antigen levels, survival estimation of head and neck cancer by the Kaplan-Meier method and Cox regression analysis, and pathologic complete response prediction of breast cancer after neoadjuvant chemotherapy. Overall accuracy and area under the receiver-operating-characteristic (AUC) curve were assessed. Results: Our approach yielded median true-positive rates of 0.75, 0.85, 0.87, and 0.75 and median Dice similarity coefficients of 0.81, 0.76, 0.83, and 0.73 for patients with lung cancer, melanoma, lymphoma, and prostate cancer, respectively, on the tumor segmentation task. The risk model for prostate cancer yielded an overall accuracy of 0.83 and an AUC of 0.86. Patients classified as low- to intermediate- and high-risk had mean follow-up prostate-specific antigen levels of 18.61 and 727.46 ng/mL, respectively (P < 0.05). The risk score for head and neck cancer was significantly associated with overall survival by univariable and multivariable Cox regression analyses (P < 0.05). Predictive models for breast cancer predicted pathologic complete response using only pretherapy imaging measures and both pre- and posttherapy measures with accuracies of 0.72 and 0.84 and AUCs of 0.72 and 0.76, respectively. Conclusion: The proposed approach demonstrated accurate tumor segmentation and prognosis in patients across 6 cancer types on 18F-FDG and PSMA PET/CT scans.
引用
- Leung KH, Rowe SP, Sadaghiani MS, et al. Deep Semisupervised Transfer Learning for Fully Automated Whole-Body Tumor Quantification and Prognosis of Cancer on PET/CT. J Nucl Med. 2024. PMID: 38423786. doi:10.2967/jnumed.123.267048
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。